Python – tensorflow.math.zero_fraction()

TensorFlow is open-source Python library designed by Google to develop Machine Learning models and deep learning  neural networks.

zero_fraction() is used to find fraction of zeros in value.

Syntax: tensorflow.math.zero_fraction(value, name)

Parameters:

• value: It’s a tensor of numeric type.
• name(optional): It defines the name for the operation.

Returns: It returns fraction of zeros in value, with dtype float32.

Example 1:

Python3

# importing the library
import tensorflow as tf

# Initializing the input tensor
a = tf.constant([ 5, 0, 9, 15], dtype = tf.float64)

# Printing the input tensor
print('a: ', a)

# Calculating result
res = tf.math.zero_fraction(a)

# Printing the result
print('Result: ', res)

Output:

a:  tf.Tensor([ 5.  0.  9. 15.], shape=(4, ), dtype=float64)
Result:  tf.Tensor(0.25, shape=(), dtype=float32)

Example 2:

Python3

# importing the library
import tensorflow as tf

# Initializing the input tensor
a = tf.constant([ 5 + 3j, 0 + 0j, 9-6j, 0 + 0j], dtype = tf.complex128)

# Printing the input tensor
print('a: ', a)

# Calculating result
res = tf.math.zero_fraction(a)

# Printing the result
print('Result: ', res)

Output:

a:  tf.Tensor([5.+3.j 0.+0.j 9.-6.j 0.+0.j], shape=(4, ), dtype=complex128)
Result:  tf.Tensor(0.5, shape=(), dtype=float32)